mugib_voice 0.7.2

Voice SDK for Mugib — re-exports voice APIs from mugib_sdk. Prefer mugib_sdk for new projects.

0.7.2

• Depends on mugib_sdk ^1.0.4 (SSE streaming fix, Mugib Voice AI rebrand)
• Docs synced to latest SDK versions

0.7.1

• Depends on mugib_sdk ^1.0.1; docs aligned with unified SDK scope.

0.7.0

• Re-exports voice APIs from unified mugib_sdk package
• New projects should depend on mugib_sdk for chat + voice

0.6.1

• Docs: README quick-start split (basic vs optional payload), API reference for MugibVoiceCallOptions, updated docs/voice-integration.md, example README, and PUBLISHING guide.

0.6.0

• Feat: user context / payload for voice calls — pass MugibVoiceCallOptions to MugibVoiceClient.start() with userContext (inline map) and/or chatSessionId (reuse payload from chat REST API). The SDK sends a WebSocket context frame before audio and supports chat_session on the stream URL.

0.5.0

• Breaking: Removed VAPI support. The SDK now connects exclusively over Mugib Voice AI. The vapi dependency, VapiVoiceSession, and the VAPI-specific token fields (MugibVoiceToken.vapiToken / .assistantId) and isVapi getters have been removed. provider now defaults to the Mugib Voice AI backend id. MugibVoiceClient always uses the Mugib Voice AI session — no provider branching.

0.4.1

• Fix: Mugib Voice AI second call had no audio. The PCM engine was released on every end()/dispose(); re-setup() on the next call failed silently. The engine is now set up once (process-wide) and kept alive across calls — cleanup just stops feeding it instead of releasing.

0.4.0

• Feat: session resumption — Mugib Voice AI calls now preserve conversation context across network drops. The SDK stores the resumption handle sent by the Mugib server and reattaches automatically on reconnect. No new API surface; existing maxReconnectAttempts controls retry count.
• Feat: proactive reconnect on goAway — when the server signals an imminent disconnect, the SDK reconnects immediately using the latest handle.
• Backend: sessionResumption is now enabled in the Mugib Voice AI setup message; the server relays resume and goaway frames and skips the greeting on resumed connections.

0.3.1

• Fix: the start() fallback path now carries MugibVoiceErrorCode.unknown and emits on errorEvents (previously only thrown without a code).
• Docs: full README reference for all MugibVoiceErrorCode values, MugibCallMetrics fields, and the Mugib Voice AI auto-reconnect behavior.

0.3.0

• Feat: structured errors — new MugibVoiceErrorCode enum and errorEvents stream (Stream<MugibVoiceError>) alongside the existing errors string stream. MugibVoiceException now carries a code.
• Feat: latency metrics — new metrics stream and currentMetrics (MugibCallMetrics) reporting time-to-first-audio and per-response latency (Mugib Voice AI) / connection latency (VAPI).
• Feat: call timer — callDuration getter and durationTicks stream.
• Feat: automatic reconnect for Mugib Voice AI after an unexpected WebSocket drop (configurable via maxReconnectAttempts / reconnectBackoff).
• Feat: tunable playback latency for Mugib Voice AI via feedThresholdFrames (default lowered from ~333ms to ~166ms).

0.2.5

• Polish: avoid duplicate error events during Mugib Voice AI session setup failure.

0.2.4

• Fix: start() resets to idle when token fetch or session setup fails (retry without end()).
• Fix: Mugib Voice AI start() now awaits server ready (parity with VAPI call-start wait).

0.2.3

• README/docs: Mugib-centric integration guide; provider is display-only.

0.2.2

• Same reliability fixes as 0.2.1 (republish with audit-complete code).

0.2.1

• Fix: reuse same MugibVoiceClient after end() (session cleanup).
• Fix: rollback failed start() so retry works.
• Fix: VAPI awaits call-start / surfaces call-error; mic permission pre-check.
• Fix: Mugib Voice AI ready setup timeout (25s).
• Fix: HTTP client request timeout (30s).

0.2.0

• Unified SDK: VAPI + Mugib Voice AI in one MugibVoiceClient (fetches /token automatically).
• Bundled vapi package for VAPI agents — app only needs apiKey + agentId.
• MugibVoice.listAgents() — lists active agents with provider for picker UI.
• MugibAgentSummary / MugibVoiceToken models.
• Verified: flutter analyze (0 issues), flutter test (10 passing).

0.1.0

• Initial release.
• MugibVoiceClient with real-time mic capture (PCM 16 kHz), playback (PCM 24 kHz), live transcripts, call-state stream, mute, and barge-in interruption handling.
• Mugib Voice AI WebSocket stream via Mugib backend.
• Verified: flutter analyze (0 issues), flutter test (5 passing).
• Fixes: iOS playAndRecord session, mic gated until ready, cleanup race guard, AudioRecorder.dispose(), ambiguous IosAudioCategory import, async PCM feed.